Towards Training GNNs using Explanation Directed Message Passing

1 code implementation • 30 Nov 2022 • Valentina Giunchiglia, Chirag Varun Shukla, Guadalupe Gonzalez, Chirag Agarwal

With the increasing use of Graph Neural Networks (GNNs) in critical real-world applications, several post hoc explanation methods have been proposed to understand their predictions.

Unsupervised Network Embedding Beyond Homophily

1 code implementation • 21 Mar 2022 • Zhiqiang Zhong, Guadalupe Gonzalez, Daniele Grattarola, Jun Pang

Here, we formulate the unsupervised NE task as an r-ego network discrimination problem and develop the SELENE framework for learning on networks with homophily and heterophily.

Network Embedding Self-Supervised Learning

Graph Attentional Autoencoder for Anticancer Hyperfood Prediction

no code implementations • 16 Jan 2020 • Guadalupe Gonzalez, Shunwang Gong, Ivan Laponogov, Kirill Veselkov, Michael Bronstein

Recent research efforts have shown the possibility to discover anticancer drug-like molecules in food from their effect on protein-protein interaction networks, opening a potential pathway to disease-beating diet design.

General Classification Graph Classification

Learning Interpretable Disease Self-Representations for Drug Repositioning

1 code implementation • 14 Sep 2019 • Fabrizio Frasca, Diego Galeano, Guadalupe Gonzalez, Ivan Laponogov, Kirill Veselkov, Alberto Paccanaro, Michael M. Bronstein

Here, we propose an interpretable model that learns disease self-representations for drug repositioning.

Inductive Bias